A Study on the Evaluation of Relevance Feedback in Multi-tagged Image Datasets

2011 ◽  
Author(s):  
Roberto Tronci ◽  
Luisa Falqui ◽  
Luca Piras ◽  
Giorgio Giacinto
Keyword(s):  
Relevance Feedback ◽  
Image Datasets

tudi Kelayakan dan Perancangan Aplikasi Pencarian Buku pada Katalog Perpustakaan Menggunakan Rocchio Relevance Feedback

2017 ◽  
Vol 8 (1) ◽  
Author(s):  
Albert Albert ◽  
Marcel Bonar Kristanda ◽  
Seng Hansun
Keyword(s):  
Relevance Feedback ◽  
Mobile Application ◽  
Library Catalog ◽  
Feedback Method ◽  
Relevant Calculation

A catalog is a register of all bibliographic items found in a library. A bibliographic item can be any information entity. The library catalog has evolved from manual, website based catalog to mobile catalog. Unfortunately, there are still many obstacles in the results of library catalog search, including the relevant results of documents based on input from the user. The purpose of this research is to make the library catalog based on mobile application in android using relevant calculation used rocchio relevance feedback method. Terms— android, library, library catalog, mobile, rocchio.

Rancang Bangun Aplikasi UMN Library Catalog Menggunakan Metode Rocchio Relevance Feedback

2018 ◽  
Vol 9 (1) ◽  
pp. 9-17
Author(s):  
Marcel Bonar Kristanda ◽  
Seng Hansun ◽  
Albert Albert
Keyword(s):  
Information System ◽  
User Experience ◽  
Relevance Feedback ◽  
Android Application ◽  
Library Catalog ◽  
Relevant Result ◽  
User Query ◽  
Index Terms ◽  
Feedback Method ◽  
F Measure

Library catalog is a documentation or list of all library collections. Unfortunately, there is a problem identified in the process of searching a book inside library catalog in Universitas Multimedia Nusantara’s library information system regarding the relevant result based on user query input. This research aims to design and build a library catalog application on Android platform in order to increase the relvancy of searching result in a database using calculated Rocchio Relevance Feedback method along with user experience measurement. User experience analysis result presented a good respond with 91.18% score based by all factor and relevance value present 71.43% precision, 100% recall, and 83.33% F-Measure. Differences of relevant results between the Senayan Library Information system (SLiMS) and the new Android application ranged at 36.11%. Therefore, this Android application proved to give relevant result based on relevance rank. Index Terms—Rocchio, Relevance, Feedback, Pencarian, Buku, Aplikasi, Android, Perpustakaan.

scholarly journals Active Learning with Bayesian UNet for Efficient Semantic Image Segmentation

2021 ◽  
Vol 7 (2) ◽  
pp. 37
Author(s):  
Isah Charles Saidu ◽  
Lehel Csató
Keyword(s):  
Neural Network ◽  
Image Segmentation ◽  
Active Learning ◽  
Convolutional Neural Network ◽  
Medical Image ◽  
Segmentation Method ◽  
Semantic Image Segmentation ◽  
Batch Normalization ◽  
Set Up ◽  
Image Datasets

We present a sample-efficient image segmentation method using active learning, we call it Active Bayesian UNet, or AB-UNet. This is a convolutional neural network using batch normalization and max-pool dropout. The Bayesian setup is achieved by exploiting the probabilistic extension of the dropout mechanism, leading to the possibility to use the uncertainty inherently present in the system. We set up our experiments on various medical image datasets and highlight that with a smaller annotation effort our AB-UNet leads to stable training and better generalization. Added to this, we can efficiently choose from an unlabelled dataset.

scholarly journals PicPreview and PicSummary: Two Timesaving Plugins for the Fluorescence Microscopist

Cells ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 846
Author(s):  
Gabrielle Vieyres
Keyword(s):  
Fluorescence Microscopy ◽  
Biological Diversity ◽  
Supplementary Data ◽  
Video Tutorial ◽  
Daunting Task ◽  
Image Datasets

This article targets cell biologists who use fluorescence microscopy but lack automatic tools to summarize and manage their image datasets. When using microscopy to document a phenotype, multiple and random pictures are required to reflect the biological diversity of each imaged sample. Managing, integrating and summarizing the acquired data can be a daunting task that becomes extremely time-consuming unless one automatizes it. Unfortunately, if many biologists use microscopy, only a few have automatized procedures to cope with the data generated. For the majority of microscope users, the two developed complementary ImageJ plugins, PicPreview and PicSummary, will allow, in a few clicks and in an instant, to obtain an overview of all pictures taken for each sample of an experiment and a summary with one user-defined representative picture per sample. The plugins and a video tutorial, as well as demonstration pictures, are available as supplementary data at the journal website. PicPreview and PicSummary should save precious time in managing microscopy datasets and in preparing figures for publications.

Sign in / Sign up

Export Citation Format

Share Document